{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T01:26:56Z","timestamp":1786584416312,"version":"build-2736575974"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":71,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["Grant Nos. 24BJY086 and 23FGLB024"],"award-info":[{"award-number":["Grant Nos. 24BJY086 and 23FGLB024"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-55746-9","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T09:17:10Z","timestamp":1780478230000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ARUDet: active retrieval and uncertainty-aware detection for sports video object detection"],"prefix":"10.1038","volume":"16","author":[{"given":"Lijing","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinqi","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"55746_CR1","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/MIS.2025.3597120","volume":"40","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Chen, H., Rida, I. & Zhu, X. A generative random modality dropout framework for robust multimodal emotion recognition. IEEE Intell. Syst. 40, 62\u201369 (2025).","journal-title":"IEEE Intell. Syst."},{"key":"55746_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3562164","author":"H Chen","year":"2025","unstructured":"Chen, H., Liu, H., Wu, Z., Fan, X. & Cao, L. Fedsi: Federated subnetwork inference for efficient uncertainty quantification. IEEE Trans. Neural Netw. Learn. Syst. https:\/\/doi.org\/10.1109\/TNNLS.2025.3562164 (2025).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"55746_CR3","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/s10994-026-07039-5","volume":"115","author":"H Chen","year":"2026","unstructured":"Chen, H., Fan, X., Wu, Z. & Cao, L. Figbo: A generalized acquisition function framework with look-ahead capability for bayesian optimization. Mach. Learn. 115, 110 (2026).","journal-title":"Mach. Learn."},{"key":"55746_CR4","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. neural information processing systems\u00a028, (2015)."},{"key":"55746_CR5","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, 2980\u20132988 (2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"55746_CR6","doi-asserted-by":"crossref","unstructured":"Carion, N. End-to-end object detection with transformers. In European conference on computer vision 213\u2013229 (Springer, 2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"55746_CR7","unstructured":"Zhu, X. Deformable detr: Deformable transformers for end-to-end object detection (2020) arXiv preprint arXiv:2010.04159."},{"key":"55746_CR8","doi-asserted-by":"crossref","unstructured":"Meng, D. Conditional detr for fast training convergence. In Proceedings of the IEEE\/CVF international conference on computer vision 3651\u20133660 (2021).","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"55746_CR9","unstructured":"Liu, S. et al. Dab-detr: Dynamic anchor boxes are better queries for detr. arxiv 2022. arXiv preprint arXiv:2201.12329."},{"key":"55746_CR10","unstructured":"Zhang, H. et al. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"55746_CR11","doi-asserted-by":"crossref","unstructured":"Zhao, Y. Detrs beat yolos on real-time object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 16965\u201316974 (2024).","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"55746_CR12","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A. & Abbeel, P. Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"55746_CR13","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y. & Luo, P. Diffusiondet: Diffusion model for object detection. In Proceedings of the IEEE\/CVF international conference on computer vision, 19830\u201319843 (2023).","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"55746_CR14","doi-asserted-by":"crossref","unstructured":"Li, L. H. Grounded language-image pre-training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 10965\u201310975 (2022).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"55746_CR15","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L. & Wei, Y. Deep feature flow for video recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2349\u20132358 (2017).","DOI":"10.1109\/CVPR.2017.441"},{"key":"55746_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L. & Wei, Y. Flow-guided feature aggregation for video object detection. In Proceedings of the IEEE international conference on computer vision, 408\u2013417 (2017).","DOI":"10.1109\/ICCV.2017.52"},{"key":"55746_CR17","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L. & Shi, J. Object detection in video with spatiotemporal sampling networks. In Proceedings of the European Conference on Computer Vision (ECCV), 331\u2013346 (2018).","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"55746_CR18","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N. & Zhang, Z. Sequence level semantics aggregation for video object detection. In Proceedings of the IEEE\/CVF international conference on computer vision, 9217\u20139225 (2019).","DOI":"10.1109\/ICCV.2019.00931"},{"key":"55746_CR19","doi-asserted-by":"crossref","unstructured":"Deng, J. Relation distillation networks for video object detection. In Proceedings of the IEEE\/CVF international conference on computer vision 7023\u20137032 (2019).","DOI":"10.1109\/ICCV.2019.00712"},{"key":"55746_CR20","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H. & Wang, L. Memory enhanced global-local aggregation for video object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 10337\u201310346 (2020).","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"55746_CR21","doi-asserted-by":"publisher","first-page":"7853","DOI":"10.1109\/TPAMI.2022.3223955","volume":"45","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q. et al. Transvod: End-to-end video object detection with spatial-temporal transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 7853\u20137869 (2022).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"55746_CR22","doi-asserted-by":"crossref","unstructured":"Sarkar, S. Maskvd: Region masking for efficient video object detection. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) 1955\u20131964 (IEEE, 2025).","DOI":"10.1109\/WACV61041.2025.00197"},{"key":"55746_CR23","doi-asserted-by":"crossref","unstructured":"Hashmi, K.\u00a0A., Sheikh, T.\u00a0U., Stricker, D. & Afzal, M.\u00a0Z. Beyond boxes: Mask-guided spatio-temporal feature aggregation for video object detection. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), 8122\u20138133 (IEEE, 2025).","DOI":"10.1109\/WACV61041.2025.00788"},{"key":"55746_CR24","doi-asserted-by":"crossref","unstructured":"Cioppa, A. Soccernet-tracking: Multiple object tracking dataset and benchmark in soccer videos. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 3491\u20133502 (2022).","DOI":"10.1109\/CVPRW56347.2022.00393"},{"key":"55746_CR25","doi-asserted-by":"crossref","unstructured":"Cui, Y. Sportsmot: A large multi-object tracking dataset in multiple sports scenes. In Proceedings of the IEEE\/CVF international conference on computer vision 9921\u20139931 (2023).","DOI":"10.1109\/ICCV51070.2023.00910"},{"key":"55746_CR26","doi-asserted-by":"crossref","unstructured":"Khanna, D., Bright, J., Chen, Y. & Zelek, J. Sportmamba: Adaptive non-linear multi-object tracking with state space models for team sports. In Proceedings of the Computer Vision and Pattern Recognition Conference, 6143\u20136153 (2025).","DOI":"10.1109\/CVPRW67362.2025.00611"},{"key":"55746_CR27","doi-asserted-by":"crossref","unstructured":"Chen, H.-Q., Liao, C.-C., Sun, Y.-H., Lin, C.-K. & Tseng, Y.-C. Fieldmot: A field-registered multi-object tracking for sports videos. In Proceedings of the Computer Vision and Pattern Recognition Conference, 5894\u20135904 (2025).","DOI":"10.1109\/CVPRW67362.2025.00587"},{"key":"55746_CR28","first-page":"1","volume":"62","author":"B Lin","year":"2024","unstructured":"Lin, B. et al. Motion-aware correlation filter-based object tracking in satellite videos. IEEE Trans. Geosci. Remote Sens. 62, 1\u201313 (2024).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"55746_CR29","doi-asserted-by":"crossref","unstructured":"Xue, Y. Fmtrack: Frequency-aware interaction and multi-expert fusion for rgb-t tracking. In IEEE Transactions on Circuits and Systems for Video Technology (2025).","DOI":"10.1109\/TCSVT.2025.3601598"},{"key":"55746_CR30","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.1109\/TCSVT.2024.3486347","volume":"35","author":"C Xue","year":"2024","unstructured":"Xue, C., Zhong, B., Liang, Q., Xia, H. & Song, S. Unifying motion and appearance cues for visual tracking via shared queries. IEEE Transactions on Circuits and Systems for Video Technology 35, 1987\u20131998 (2024).","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"55746_CR31","doi-asserted-by":"crossref","unstructured":"Xue, C. Similarity-guided layer-adaptive vision transformer for uav tracking. In Proceedings of the Computer Vision and Pattern Recognition Conference 6730\u20136740 (2025).","DOI":"10.1109\/CVPR52734.2025.00631"},{"key":"55746_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T. & Jiang, Y. Acquisition of localization confidence for accurate object detection. In Proceedings of the European conference on computer vision (ECCV), 784\u2013799 (2018).","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"55746_CR33","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 658\u2013666 (2019).","DOI":"10.1109\/CVPR.2019.00075"},{"key":"55746_CR34","doi-asserted-by":"crossref","unstructured":"He, Y., Zhu, C., Wang, J., Savvides, M. & Zhang, X. Bounding box regression with uncertainty for accurate object detection. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition, 2888\u20132897 (2019).","DOI":"10.1109\/CVPR.2019.00300"},{"key":"55746_CR35","doi-asserted-by":"crossref","unstructured":"Hall, D. Probabilistic object detection: Definition and evaluation. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision 1031\u20131040 (2020).","DOI":"10.1109\/WACV45572.2020.9093599"},{"key":"55746_CR36","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X. et al. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. Advances in neural information processing systems 33, 21002\u201321012 (2020).","journal-title":"Advances in neural information processing systems"},{"key":"55746_CR37","doi-asserted-by":"crossref","unstructured":"Li, X. Generalized focal loss v2: Learning reliable localization quality estimation for dense object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 11632\u201311641 (2021).","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"55746_CR38","unstructured":"Cui, P. Exploring aleatoric uncertainty in object detection via vision foundation models (2024) arXiv preprint arXiv:2411.17767."},{"key":"55746_CR39","doi-asserted-by":"crossref","unstructured":"Giloni, A. Dil: An explainable and practical metric for abnormal uncertainty in object detection. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) 2507\u20132516 (IEEE, 2025).","DOI":"10.1109\/WACV61041.2025.00249"},{"key":"55746_CR40","doi-asserted-by":"crossref","unstructured":"Sun, H., Li, Y., Yang, L., Cao, X. & Zhang, B. Uncertainty-aware gradient stabilization for small object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 8407\u20138417 (2025).","DOI":"10.1109\/ICCV51701.2025.00787"},{"key":"55746_CR41","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, Y., Zhu, X., Chang, Y. & Gao, Y. Dualadaptnet: Enhancing domain adaptation regression with error accumulation reduction and dual-head heterogeneous learning. Pattern Recognit.\u00a0112641 (2025).","DOI":"10.1016\/j.patcog.2025.112641"},{"key":"55746_CR42","unstructured":"Luo, T. Dig-face: De-biased learning for generalized facial expression category discovery (2024) arXiv preprint arXiv:2409.20098."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55746-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55746-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55746-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:29:26Z","timestamp":1786580966000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55746-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,3]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["55746"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-55746-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,3]]},"assertion":[{"value":"11 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25264"}}